Anthropic says Fable 5 has invisible safeguards that use prompt modification, steering vectors, or PEFT to limit its effectiveness for frontier LLM development (Matthias Bastian/The Decoder)

1 hour ago 1
Add to circle

Matthias Bastian / The Decoder:
Anthropic says Fable 5 has invisible safeguards that use prompt modification, steering vectors, or PEFT to limit its effectiveness for frontier LLM development  —  Key Points … Ask about this article...  Both models share the same base model.  Fable 5 ships with conservative safety guardrails for general use.

Read Entire Article